telnyx-ai-inference-curl

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports crawling and ingesting arbitrary website content via the "POST /ai/embeddings/url" (Embed URL content) endpoint in SKILL.md (and also accepts external file URLs for transcription/summarization), which allows untrusted public web pages to be fetched and encoded into embeddings/summaries that the agent would read and act on.